CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
arXiv: Computer Vision and Pattern Recognition, 2019.
Objects in an image exhibit diverse scales. Adaptive receptive fields are expected to catch suitable range of context for accurate pixel level semantic prediction for handling objects of diverse sizes. Recently, atrous convolution with different dilation rates has been used to generate features of multi-scales through several branches and...More
PPT (Upload PPT)